Pinterest has always prioritized user experiences. Yunsong Guo explores how Pinterest uses machine learning—particularly linear, gradient-boosted decision trees, and deep neural network models—in its most important product, the home feed, to improve user engagement. Along the way, Yunsong shares how Pinterest drastically increased its international user engagement along with lessons on finding the most impactful features.
Yunsong Guo is a staff engineer at Pinterest developing home feed ranking ML models. Yunsong is the founding member of the home feed ranking team and has led key projects to turn Pinterest home feed ranking from time based to logistic regression based and later to GBDT-powered ranking systems. Such projects and feature improvements resulted in more than 100% home feed user engagement gains. Previously, he spent a few years working in London and Hong Kong on algorithmic trading, high-frequency trading, and statistical arbitrage using machine-learned models. Yunsong holds a PhD in computer science from Cornell University with a focus on machine learning.
Comments on this page are now closed.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com